Codex, Behind the Harness: Dominik Kundel on OpenAI's Codex
In an AI Engineer talk, OpenAI's Dominik Kundel explains how Codex switched to websocket mode when GPT 5.3 Codex Spark hit 1,000 tokens/sec on Cerebras, making inference no longer the bottleneck. The persistent connection carries stateful context, shipping only the turn's changes.
Featured · Dominik Kundel
1 source
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Z.ai CEO Jie Tang: GLM 5.3 gains come from RL, not parameter count
- New tool adds 14 skills to Claude Code and Cursor for Markdown diagrams
- Tool turns Claude into a team of AI employees on your Mac
- GOP panics over Big Tech ties as Trump shifts on AI regulation
- Ethan Mollick: Claude's skill creator beats ChatGPT for reusable skills